Hope Agent is a cross-device personal AI assistant that remembers context, uses tools, and continues working toward goals through dynamically organized workflows. Individuals use it from desktop, web, server, or messaging environments to manage projects, knowledge, designs, and long-running tasks. The catalogue add-ons extend its agent workflows and capabilities.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add shiwenwen/hope-agent --skill email-draftgit clone --depth 1 https://github.com/shiwenwen/hope-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shiwenwen/hope-agent/email-draft)<a href="https://agentmods.dev/skills/shiwenwen/hope-agent/email-draft"><img src="https://agentmods.dev/badge/skills/shiwenwen/hope-agent/email-draft.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 162 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.01491 |
| Opus 5 | $0.00023 | $0.00745 |
| Sonnet 5 | $0.00009 | $0.00298 |
| Haiku 4.5 | $0.00005 | $0.00149 |
Grade A, and why
email-draft scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Draft
When to Use
Trigger phrases: "draft an email", "reply to this email", "polish this email", "翻译这封邮件", "write an email to ".
Don't trigger for: chat messages, Slack DMs, in-app notifications, marketing copy. Those are different formats.
Output Format
Always produce the draft in this layout. Use a fenced code block so the user can copy it cleanly:
Subject: <concise, action-oriented, ≤60 chars>
Hi <Name>,
<opening line — context or thanks>
<body — one focused paragraph per point, max 3 paragraphs>
<call to action / next step / explicit ask>
Best,
<Sender>
If the language isn't English, adapt greeting and sign-off to the local convention:
- 中文:
<Name>，你好/祝好，<Sender> - 日本語:
<Name>様/よろしくお願いいたします。<Sender> - Français:
Bonjour <Name>,/Cordialement, <Sender> - 한국어:
<Name>님께/감사합니다, <Sender>
Workflow
-
Clarify minimal essentials via
ask_user_questionif missing:- Recipient and rough relationship (peer / manager / external client / cold outreach)
- One-sentence purpose ("schedule a meeting" / "decline a vendor" / "ask for clarification")
- Tone (formal / collegial / brief)
- Preferred language
- Any constraints to mention (deadline, budget, link to attachment)
-
Subject line first — the subject is what gets read. Make it specific and action-oriented:
- Bad: "Quick question"
- Good: "Q3 budget approval — need sign-off by Friday"
- Bad: "Following up"
- Good: "Followup on June 12 design review action items"
-
Body — three paragraph max:
- Paragraph 1: context / why you're writing
- Paragraph 2: the specific request, decision, or information
- Paragraph 3: clear next step (what you want them to do, by when)
-
Pre-Send Self-Check — after producing the draft, run through this checklist out loud (in your reply to the user, before the draft):
- Subject is specific and action-oriented (not "Hi" / "Question")
- Recipient name is correct (no "Hi " placeholder left)
- Purpose stated in the first 2 sentences
- Concrete ask with deadline, not vague
- No internal jargon if recipient is external
- Tone matches relationship (formal vs collegial)
- No accidental "Reply All" implications (if forwarding, mention)
- No PII / secrets that shouldn't be in email
- Attachments mentioned in body if any
- Sign-off matches the user's actual name
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 186 lines · 46 tokens per session scan A 4b5418f2e17b
email-draft is a skill published in the GitHub repository shiwenwen/hope-agent (1,561 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,491 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
memory
Use this skill when Pioneer should proactively use durable memory or recalled context: decide whether memory can improve a turn, answer from remembered user/project facts, request memory tools, search/list/get stored memories, save durable preferences or project decisions, forget memories, audit or clean up memory, or…
subagents
Use this skill when Pioneer should delegate current-turn work to attached task-backed subagents, coordinate parallel child agents, wait for child results, review/revise/accept/cancel/detach attached work, or synthesize accepted child results into the parent answer.
tasks
Use this skill when Pioneer should create, inspect, update, reschedule, pause, resume, troubleshoot, or configure delivery for durable tasks, scheduled tasks, recurring tasks, interval tasks, cron jobs, background work, or existing task state.
browser
Headless web browsing: navigation, page inspection, interaction, data extraction, screenshots, PDFs, and browser session management.
technology-search
Search tech blogs, developer forums, and IT media (TechCrunch, Hacker News, 36氪, etc.) for software and hardware industry updates with heat ranking and EN↔CN translation. Use this skill only when the topic is clearly about programming, software, hardware, AI, or IT infrastructure.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.